de_mlm_child_13_new
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9684
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 13
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.2096 | 2000 | 7.0534 |
| 7.005 | 2.4191 | 4000 | 5.9491 |
| 7.005 | 3.6287 | 6000 | 5.8401 |
| 5.5533 | 4.8382 | 8000 | 5.7121 |
| 5.5533 | 6.0478 | 10000 | 5.6198 |
| 5.3687 | 7.2573 | 12000 | 5.5387 |
| 5.3687 | 8.4669 | 14000 | 5.4706 |
| 5.2269 | 9.6764 | 16000 | 5.4217 |
| 5.2269 | 10.8860 | 18000 | 5.3631 |
| 5.1229 | 12.0956 | 20000 | 5.3213 |
| 5.1229 | 13.3051 | 22000 | 5.2743 |
| 5.0061 | 14.5147 | 24000 | 4.9732 |
| 5.0061 | 15.7242 | 26000 | 4.2903 |
| 4.0671 | 16.9338 | 28000 | 3.7955 |
| 4.0671 | 18.1433 | 30000 | 3.5115 |
| 3.3253 | 19.3529 | 32000 | 3.3390 |
| 3.3253 | 20.5624 | 34000 | 3.1444 |
| 2.969 | 21.7720 | 36000 | 2.9896 |
| 2.969 | 22.9816 | 38000 | 2.8436 |
| 2.6828 | 24.1911 | 40000 | 2.7259 |
| 2.6828 | 25.4007 | 42000 | 2.6287 |
| 2.4634 | 26.6102 | 44000 | 2.5300 |
| 2.4634 | 27.8198 | 46000 | 2.4772 |
| 2.317 | 29.0293 | 48000 | 2.4356 |
| 2.317 | 30.2389 | 50000 | 2.3599 |
| 2.2136 | 31.4484 | 52000 | 2.3320 |
| 2.2136 | 32.6580 | 54000 | 2.3017 |
| 2.1362 | 33.8676 | 56000 | 2.2597 |
| 2.1362 | 35.0771 | 58000 | 2.2461 |
| 2.0753 | 36.2867 | 60000 | 2.2101 |
| 2.0753 | 37.4962 | 62000 | 2.1714 |
| 2.0214 | 38.7058 | 64000 | 2.1669 |
| 2.0214 | 39.9153 | 66000 | 2.1505 |
| 1.9757 | 41.1249 | 68000 | 2.1361 |
| 1.9757 | 42.3344 | 70000 | 2.0909 |
| 1.9433 | 43.5440 | 72000 | 2.0859 |
| 1.9433 | 44.7536 | 74000 | 2.0732 |
| 1.9082 | 45.9631 | 76000 | 2.0745 |
| 1.9082 | 47.1727 | 78000 | 2.0481 |
| 1.8821 | 48.3822 | 80000 | 2.0327 |
| 1.8821 | 49.5918 | 82000 | 2.0211 |
| 1.8581 | 50.8013 | 84000 | 2.0263 |
| 1.8581 | 52.0109 | 86000 | 2.0064 |
| 1.8359 | 53.2204 | 88000 | 2.0034 |
| 1.8359 | 54.4300 | 90000 | 1.9978 |
| 1.8159 | 55.6396 | 92000 | 1.9832 |
| 1.8159 | 56.8491 | 94000 | 1.9772 |
| 1.8051 | 58.0587 | 96000 | 1.9930 |
| 1.8051 | 59.2682 | 98000 | 1.9752 |
| 1.794 | 60.4778 | 100000 | 1.9684 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 15